Fast discovery of association rules
Advances in knowledge discovery and data mining
Data mining: concepts and techniques
Data mining: concepts and techniques
A condensed representation to find frequent patterns
PODS '01 Proceedings of the twentieth ACM SIGMOD-SIGACT-SIGART symposium on Principles of database systems
Concise Representation of Frequent Patterns Based on Disjunction-Free Generators
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Mining All Non-derivable Frequent Itemsets
PKDD '02 Proceedings of the 6th European Conference on Principles of Data Mining and Knowledge Discovery
Concise Representation of Frequent Patterns Based on Generalized Disjunction-Free Generators
PAKDD '02 Proceedings of the 6th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Constraint-Based Discovery and Inductive Queries: Application to Association Rule Mining
Proceedings of the ESF Exploratory Workshop on Pattern Detection and Discovery
Constraining and summarizing association rules in medical data
Knowledge and Information Systems
Comparing association rules and decision trees for disease prediction
HIKM '06 Proceedings of the international workshop on Healthcare information and knowledge management
Models for association rules based on clustering and correlation
Intelligent Data Analysis
Closures of Downward Closed Representations of Frequent Patterns
HAIS '09 Proceedings of the 4th International Conference on Hybrid Artificial Intelligence Systems
Non-Derivable Item Set and Non-Derivable Literal Set Representations of Patterns Admitting Negation
DaWaK '09 Proceedings of the 11th International Conference on Data Warehousing and Knowledge Discovery
| Hi-index | 0.00 |
A number of concise lossless representations of frequent patterns were proposed. Except for closed patterns, all other representations of patterns consist of a main component and a border. Recently, a unifying framework was introduced that treats border representations as particular cases of so called k-disjunction free representations. It was shown that careful splitting of borders into subgroups allows deletion of some of such subgroups without making the representations lossy. In this paper, we propose a new method of border reduction. Our method consists in identifying patterns in the main representation's component that uniquely determine a possibly maximal subset of patterns from the group under reduction. Such itemsets are redundant and can be deleted from border's groups. The performed experiments show that the new method reduces border representations by up to two orders of magnitude.